MARES: multitask learning algorithm for Web-scale real-time event summarization

doi:10.1007/s11280-018-0597-7

CORC > 上海财经大学 > 上海财经大学

	MARES: multitask learning algorithm for Web-scale real-time event summarization
	Yang, Min 1; Tu, Wenting 2; Qu, Qiang 1; Lei, Kai 3; Chen, Xiaojun 4; Zhu, Jia 5; Shen, Ying 6
刊名	WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
	2019-03
卷号	22 期号:2 页码:499-515
关键词	Multitask learning Real-time event summarization Relevance prediction Document filtering
ISSN号	1386-145X
DOI	10.1007/s11280-018-0597-7
英文摘要	Automatic real-time summarization of massive document streams on the Web has become an important tool for quickly transforming theoverwhelming documents into a novel, comprehensive and concise overview of an event for users. Significant progresses have been made in static text summarization. However, most previous work does not consider the temporal features of the document streams which are valuable in real-time event summarization. In this paper, we propose a novel M ultitask learning A lgorithm for Web-scale R eal-time E vent S ummarization (MARES), which leverages the benefits of supervised deep neural networks as well as a reinforcement learning algorithm to strengthen the representation learning of documents. Specifically, MARES consists two key components: (i) A relevance prediction classifier, in which a hierarchical LSTM model is used to learn the representations of queries and documents; (ii) A document filtering model learns to maximize the long-term rewards with reinforcement learning algorithm, working on a shared document encoding layer with the relevance prediction component. To verify the effectiveness of the proposed model, extensive experiments are conducted on two real-life document stream datasets: TREC Real-Time Summarization Track data and TREC Temporal Summarization Track data. The experimental results demonstrate that our model can achieve significantly better results than the state-of-the-art baseline methods.
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000462231500005
内容类型	期刊论文
源URL	[http://10.2.47.112/handle/2XS4QKH4/322]
专题	上海财经大学
通讯作者	Zhu, Jia
作者单位	1.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen, Peoples R China; 2.Shanghai Univ Finance & Econ, Dept Comp Sci, Shanghai, Peoples R China; 3.Peking Univ, Sch Elect & Comp Engn, Shenzhen, Peoples R China; 4.Shenzhen Univ, Sch Comp Sci, Shenzhen, Peoples R China; 5.South China Normal Univ, Sch Comp Sci, Guangzhou, Guangdong, Peoples R China; 6.Peking Univ, Shenzhen Grad Sch, Sch Elect & Comp Engn, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Yang, Min,Tu, Wenting,Qu, Qiang,et al. MARES: multitask learning algorithm for Web-scale real-time event summarization[J]. WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS,2019,22(2):499-515.
APA	Yang, Min.,Tu, Wenting.,Qu, Qiang.,Lei, Kai.,Chen, Xiaojun.,...&Shen, Ying.(2019).MARES: multitask learning algorithm for Web-scale real-time event summarization.WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS,22(2),499-515.
MLA	Yang, Min,et al."MARES: multitask learning algorithm for Web-scale real-time event summarization".WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS 22.2(2019):499-515.